Independent vector analysis with multivariate Gaussian model: A scalable method by multilinear regression

Simple item page
dc.contributor.authorGabrielson, Ben
dc.contributor.authorSun, Mingyu
dc.contributor.authorAkhonda, Mohammad Abu Baker Siddique
dc.contributor.authorCalhoun, Vince D.
dc.contributor.authorAdali, Tulay
dc.date.accessioned2023-05-23T17:48:58Z
dc.date.available2023-05-23T17:48:58Z
dc.date.issued2023-05-05
dc.descriptionICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 04-10 June 2023en_US
dc.description.abstractJoint blind source separation (JBSS) is a powerful tool for analyzing multiple linked datasets, distinguished by the key ability to exploit cross-dataset dependencies. Despite this ability generally improving overall estimation performance, joint decompositions also incur considerable computational costs, which can lead to intractable problems with hundreds or thousands of datasets. In this paper, we introduce an efficient method for large-scale JBSS by multilinear regression. We consider a model where out of all datasets, only a selected subset are first decomposed to provide regressors that sufficiently estimate sources across all datasets. These regressors define a per-source cost function that naturally extends independent vector analysis (IVA) with a multivariate Gaussian source prior (IVA-G), a powerful formulation for exploiting cross-dataset dependencies. Using simulated and real fMRI data, we demonstrate significant advantages of this method compared with other JBSS methods.en_US
dc.description.sponsorshipThis work was supported in part by NSF-NCS 1631838, NSF 2112455, and NIH grants R01 MH118695, R01 MH123610, R01 AG073949. The hardware used in these studies is part of the UMBC High Performance Computing Facility (HPCF). HPCF is supported by the U.S. NSF through the MRI program (grant nos. CNS-0821258, CNS-1228778, and OAC-1726023) and the SCREMS program (grant no. DMS-0821311), with additional support from the University of Maryland, Baltimore County (UMBC).en_US
dc.description.urihttps://ieeexplore.ieee.org/abstract/document/10096698en_US
dc.format.extent5 pagesen_US
dc.genreconference papers and proceedingsen_US
dc.genrepostprints
dc.identifierdoi:10.13016/m24eaz-g12z
dc.identifier.citationB. Gabrielson, M. Sun, M. A. B. S. Akhonda, V. D. Calhoun and T. Adali, "Independent Vector Analysis with Multivariate Gaussian Model: a Scalable Method by Multilinear Regression," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10096698.en_US
dc.identifier.urihttps://doi.org/10.1109/ICASSP49357.2023.10096698
dc.identifier.urihttp://hdl.handle.net/11603/28059
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rights© 2023 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.subjectUMBC High Performance Computing Facility (HPCF)en_US
dc.subjectJoint Blind Source Separationen_US
dc.subjectIndependent Vector Analysisen_US
dc.subjectGroup Independent Component Analysisen_US
dc.titleIndependent vector analysis with multivariate Gaussian model: A scalable method by multilinear regressionen_US
dc.typeTexten_US
dcterms.creatorhttps://orcid.org/0000-0001-9217-6641en_US
dcterms.creatorhttps://orcid.org/0000-0003-0826-453Xen_US
dcterms.creatorhttps://orcid.org/0000-0003-0594-2796en_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Gabrielson 2023.pdf
Size:
393.07 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection